© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 1964
    Prev
    Next
    INDEX
    Explanations

    terms related to editing and editing processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    省市镇
    -0.37
    BagConstraints
    -0.35
     claimant
    -0.34
     cão
    -0.33
     ilman
    -0.33
     cromado
    -0.32
    showthread
    -0.32
    verwijspagina
    -0.32
    mybatisplus
    -0.32
    ']?>
    -0.32
    POSITIVE LOGITS
     editing
    3.17
     Editing
    2.88
     edited
    2.84
     editor
    2.77
     editors
    2.75
     edit
    2.69
    editing
    2.55
     edits
    2.52
    Editing
    2.48
    edited
    2.31
    Activations Density 0.138%

    No Known Activations